mardi 20 octobre
🌍 Open models. Open kernels. Open inference. From private deployments to public clouds, we’ll keep...
🌍 Open models. Open kernels. Open inference.From private deployments to public clouds, we’ll keep working with the community to make large-scale inference more efficient.Explore the code, contribute, and build with us!4/4
🛠️ Also open-sourcing deepseek-recipe Our production token encoding & decoding component, alig...
🛠️ Also open-sourcing deepseek-recipeOur production token encoding & decoding component, aligned with the processing logic behind the official DeepSeek API to bring the same API behavior to community deployments.🔗 htgithub.com/deepseek-ai/de…3/4
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSee...
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.�github.com/deepse…
samedi 17 octobre
🔓 Open-source release Get DeepSeek-V4.1-Flash-1017: 🤗 Hugging Face: https://t.co/PxjsLqLx2m 🔗 Mo...
🔓 Open-source releaseGet DeepSeek-V4.1-Flash-1017:🤗 Hugging Facehuggingface.co/deepseek-ai/De…2m🔗 ModelScopmodelscope.cn/models/deepsee…G2H4/4
🔍 Search & Fetch APIs are now open to everyone! Powered by our in-house search engine, serving hun...
🔍 Search & Fetch APIs are now open to everyone!Powered by our in-house search engine, serving hundreds of millions of requests daily worldwide.💰 Each endpoint: $0.75 per 1,000 calls.📖 Docapi-docs.deepseek.com/guides/searchQIr📌 Search & Fetch calls via server-side tools in DeepSeek Harness, Claude Co…
🎮 Build complete projects from scratch DeepSeek-V4.1-Flash-1017 uses reinforcement learning with s...
🎮 Build complete projects from scratchDeepSeek-V4.1-Flash-1017 uses reinforcement learning with self-feedback to improve end-to-end project development—from game creation to 3D modeling.See it in action 👇2/4
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and sh...
🚀 DeepSeek-V4.1-Flash-1017 is here!Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgr…
vendredi 2 octobre
Please check out @DeepSeekHarness. We just released packaged desktop versions for macOS and Windows;...
Please check out @DeepSeekHarness. We just released packaged desktop versions for macOS and Windows; Linux users can get it from the @deepseek-ai/dsh package on npm. deepseek.com/harnessDeepSeek Harness@DeepSeekHarnessDeepSeek Harness for desktop is now available on macOS and Windows. x.com/i/artic…
jeudi 10 septembre
🌐 Supporting open source. Expanding deployment options. We’ll work closely with the open-source co...
🌐 Supporting open source. Expanding deployment options.We’ll work closely with the open-source community on V4.1-Flash inference support and explore more deployment options.Planning a large-scale deployment with 2,000 GPUs + a storage cluster? Let’s talk.🔹 Modelhuggingface.co/deepseek-ai/De…6a🔹 Pape…
💰 More efficient architecture. Lower API prices. V4.1-Flash lets us serve more users at a lower co...
💰 More efficient architecture. Lower API prices.V4.1-Flash lets us serve more users at a lower cost. We’re passing the savings on to you.🔹 Peak/off-peak pricing continues to balance demand.🔹 Off-peak rates are 50% of peak rates. Schedule flexible workloads off-peak to save.🔹 New pricing takes effect…
⚡ V4.1-Flash is now live on the DeepSeek API with native multimodal support. Set your model to deep...
⚡ V4.1-Flash is now live on the DeepSeek API with native multimodal support.Set your model to deepseek-flash.🔹 V4-Flash & V4-Flash-Vision-Exp are retired. For compatibility, deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily route to V4.1-Flash.🔹 Tests by multiple parties put V4.1-Flash…
💾 Smaller KV cache. Bigger savings. Compared with the previous generation, V4.1-Flash’s KV cache n...
💾 Smaller KV cache. Bigger savings.Compared with the previous generation, V4.1-Flash’s KV cache needs just:🔹 1/4 the HBM🔹 1/8 the SSD storageCache-hit charges often account for a large share of agent costs. Compressing the cache cuts those costs significantly.3/6
🧠 Asymmetric architecture. More intelligence, less cost. 🔹 552B-parameter MoE. 🔹 New Causal Enco...
🧠 Asymmetric architecture. More intelligence, less cost.🔹 552B-parameter MoE.🔹 New Causal Encoder–Decoder architecture: just 8B active parameters for input, 16B for output.🔹 New pre-training methods + larger-scale RL post-training deliver benchmark results ahead of flagship models, including DeepSee…
🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest mo...
🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient.🔹 Introducing the smallest model in our new architecture family, with native visual understanding.🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models.1/6
vendredi 21 août
Multimodal API support 🔌 🔹 Set model='deepseek-v4-flash-vision-exp' 🔹 Images are tokenized for b...
Multimodal API support 🔌🔹 Set model='deepseek-v4-flash-vision-exp'🔹 Images are tokenized for billing: up to 384 tokens each, at V4-Flash pricing🔹 Supports Chat Completions, Messages & Responses🔹 Supports mixed text + image input; images can be provided via base64, external URLs, or the Files API.Dap…
Files API is now live. 📁 🔹 Free to use 🔹 Upload an image once, then reference it by file_id to s...
Files API is now live. 📁🔹 Free to use🔹 Upload an image once, then reference it by file_id to save request bandwidth🔹 Reuse the same image across requests—no need to upload it againLearn moapi-docs.deepseek.com/guides/files_a…6xmc4/n
Multimodality unlocks more agent use cases. 👀 V4-Flash-Vision-Exp works smoothly across agent fram...
Multimodality unlocks more agent use cases. 👀V4-Flash-Vision-Exp works smoothly across agent frameworks, combining visual understanding with a wide range of tools to unlock more practical workflows.2/n
DeepSeek-V4-Flash-Vision-Exp is now live on the DeepSeek API Platform! 🚀 🔹 This experimental mult...
DeepSeek-V4-Flash-Vision-Exp is now live on the DeepSeek API Platform! 🚀🔹 This experimental multimodal model matches DeepSeek-V4-Flash on text capabilities—including agents, reasoning, and world knowledge.🔹 On multimodal agent benchmarks, V4-Flash-Vision-Exp makes a major leap over V4-Flash, bringin…
jeudi 13 août
🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening it up to developer...
🧩 DeepSeek Harness v0.1 is now available in Developer Preview!🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license.🔹 Powered by the Cordis meta-framework, DeepSeek Harness is an agent harness built around one core idea: Everything is a…
API pricing update 💰 With the V4 lineup release, we’re updating our API pricing and introducing pe...
API pricing update 💰With the V4 lineup release, we’re updating our API pricing and introducing peak and off-peak rates. Off-peak rates are 50% lower than peak, enabling more flexible workload scheduling. 📉New pricing takes effect at 16:00 UTC, Aug 16, 2026 🕒
